brand-retrieve-unified
ChatGPTRetrieve machine-readable company and brand intelligence—logos, colors, descriptions, socials, links, industry, location, and more—from one domain, company name, work email, stock ticker, ISIN, transaction descriptor, or direct URL. Use get-brand for a visual card from a domain; use this tool for raw structured data or non-domain lookups.
brand-search
ChatGPTSearch indexed brands by company name or domain and return up to 10 lightweight matches. Supports prefix autocomplete, field selection, and typo tolerance. Use brand-retrieve-unified for a full profile or get-brand for a visual domain card.
cancel-batch
ChatGPTStop a queued or running batch from starting additional pages. Work already in progress finishes and unused reserved credits are refunded after settlement. This does not delete stored results; use only when the user explicitly wants processing stopped.
create-monitor
ChatGPTCreate a recurring monitor for a page, sitemap, or structured extraction target. Use this when the user wants ongoing change detection, not a one-time scrape. Configure the target, schedule, change detection, and optional webhook; Context immediately runs an initial baseline and returns the monitor.
delete-batch
ChatGPTPermanently delete a completed, cancelled, or failed batch and its stored results. Active batches must be cancelled and allowed to settle first. This cannot be undone; use only when the user explicitly requests deletion.
delete-monitor
ChatGPTPermanently delete a monitor and stop all future scheduled runs. This cannot be undone; use only when the user explicitly wants the monitor removed.
get-batch
ChatGPTRetrieve one batch's status, progress, timing, credit accounting, errors, and download links when complete. Poll this after submit-batch; use get-batch-results only after the batch has completed.
get-batch-results
ChatGPTPage through the successful and failed URL results of a completed batch as JSON. Use the returned cursor to continue when more results exist. For progress before completion, use get-batch instead.
get-brand
ChatGPTRetrieve live brand intelligence for a domain and render a visual Context card with its logo, colors, slogan, description, social profiles, industry, location, and key links. Use this when a user wants to see or inspect a company's brand. Use brand-retrieve-unified instead for raw structured data or lookup by name, email, ticker, ISIN, transaction descriptor, or direct URL.
get-change
ChatGPTRetrieve one detected change with full text diffs, added or removed URLs, semantic evidence, confidence, importance, and the current snapshot when available. Use after either change-listing tool when the complete evidence is needed.
get-log
ChatGPTRetrieve one API request from the authenticated Context account by the request_id in a list-logs data entry, including its redacted retained input, response, timing, credits, status, and user agent. Zero-data-retention requests contain metadata but no retained input or response.
get-monitor
ChatGPTRetrieve one monitor's configuration, status, schedule, target, change-detection rules, webhook settings, and current baseline by ID. This reads the monitor definition; use list-monitor-runs for execution history or list-monitor-changes for detected changes.
get-monitor-limits
ChatGPTRetrieve the authenticated account's current monitor count and maximum allowed monitors. Use before create-monitor when checking available capacity.
get-monitor-run
ChatGPTRetrieve one run for a monitor, including lifecycle status, timing, credits charged, and the detected change when present. Use after list-monitor-runs or run-monitor-now when the full outcome of one check is needed.
get-news-search
ChatGPTSearch live and historical news for one company. Provide exactly one top-level identifier: companyName, domain, ticker with an optional exchange, or isin. Set sortBy to newest or relevance. Choose at most one filter category: publisher domain, publisher country, article language, or article type; optionally add a publication date range. Use web-search for broader topics or news that is not tied to one company.
get-usage
ChatGPTGet the authenticated Context account's credit balance, credits used in the current monthly period, the next refill time and amount, and Auto-Topup status. Use this before large jobs or after a 401 USAGE_EXCEEDED to see how many credits are left and when they refill. Use get-usage-history for usage over time. Costs no credits.
get-usage-history
ChatGPTGet the authenticated Context account's credits and requests over time, bucketed by hour, day, or month (UTC, oldest first, empty buckets as zeros). Set group_by to path, key_id, or status_code to see which endpoints, API keys, or outcomes used credits. Defaults to the last 30 days by day. Use get-usage for the current balance and next refill. Costs no credits.
get-webhook-delivery
ChatGPTRetrieve one webhook delivery from the authenticated account, including its status and latest attempt. Use list-webhook-deliveries to find its delivery_id.
list-account-runs
ChatGPTList monitor runs across the authenticated account. Use this for an organization-wide activity feed or operational overview; use list-monitor-runs when only one monitor matters.
list-batches
ChatGPTList asynchronous scraping batches from newest to oldest, with status, search, tag, and cursor filters. Use this to find a batch ID or review account activity; it does not return page-level results.
list-changes
ChatGPTList detected changes across all monitors in the authenticated account, with monitor, type, time, and tag filters. Use this for an account-wide change feed; use list-monitor-changes for one monitor.
list-logs
ChatGPTList recent API requests from the authenticated Context account, newest first. Filter by time, endpoint path, API key ID, HTTP status, error code, tags, or request content. Use errors_only to investigate failures, then pass the request_id from a data entry to get-log for the retained request and response. Defaults to the last 24 hours and does not create another usage-log entry.
list-monitor-changes
ChatGPTList changes detected by one monitor, with time and tag filters. Use this for a monitor-specific change history, then call get-change when full diffs, evidence, confidence, and importance are needed.
list-monitor-credit-usage
ChatGPTReport credits charged by monitor over a time window, ordered by the monitors using the most credits. Use this for spend analysis and optimization, not for run or change details.
list-monitor-runs
ChatGPTList the execution history of one monitor, including run status, timing, credits, and whether each run detected a change. Use get-monitor-run for the full details of one run.
list-monitors
ChatGPTList recurring monitors in the authenticated Context account, with search, status, target-type, tag, and cursor filters. Use this to find a monitor ID before reading, updating, running, or deleting it; this does not return run history or detected changes.
list-webhook-deliveries
ChatGPTList the authenticated account's batch or monitor webhook deliveries, newest first. Select the source type and filter by batch, monitor, run, status, or creation time. Use get-webhook-delivery or list-webhook-delivery-attempts for delivery details.
list-webhook-delivery-attempts
ChatGPTList attempts for one webhook delivery, newest first, with delivery outcomes for troubleshooting. Use retry-webhook-delivery when another delivery attempt is needed.
parse-document
ChatGPTSend PDF, Office, spreadsheet, presentation, image, code, data, or text file bytes to Context and convert them into clean Markdown for agents, analysis, and RAG. Use this when the source is a file rather than a URL. This transformation consumes Context credits but does not alter the original file.
people-enrich
ChatGPTEnrich one person from combined identity clues and return a profile with an identity match score. Provide a person email, a person-profile social URL, or both first and last name with company, education, or location. Use brand-retrieve-unified for company data.
retry-webhook-delivery
ChatGPTQueue another attempt for a webhook delivery created within the last seven days. This can send the event to its configured external receiver again. Use get-webhook-delivery or list-webhook-delivery-attempts to inspect the outcome.
rotate-monitor-webhook-secret
ChatGPTReplace a monitor's webhook signing secret and return its updated configuration. The previous secret stops signing deliveries immediately; update the webhook receiver to use the returned secret. Requires a monitor with a configured webhook URL.
run-monitor-now
ChatGPTQueue an immediate check for a monitor outside its regular schedule. This starts an asynchronous network run, may advance the monitor's stored comparison baseline, and can notify its configured external webhook when a change is detected. Use get-monitor-run or list-monitor-runs to follow its outcome. Paused monitors return 409 MONITOR_PAUSED. Setting status=active with update-monitor already runs the monitor promptly; don't call run-monitor-now right after resuming or its run may be skipped as superseded.
submit-batch
ChatGPTStart an asynchronous job to scrape up to 25,000 supplied URLs or crawl a large website as Markdown or HTML. Use this when a synchronous scrape or crawl would be too large. When webhookUrl is supplied, Context sends a completion request to that external endpoint. The call returns a batch ID, not page results; use get-batch until it settles, then get-batch-results. Supply an Idempotency-Key when a submission may be retried.
submit-feedback
ChatGPTReport a Context problem to the Context team. Always use this when a tool or API behaves unexpectedly, including wrong or incomplete successful results, unexpected errors, or a docs mismatch, even after a successful workaround. Never use it for account limits working as intended: 401 USAGE_EXCEEDED, 429 RATE_LIMITED, or 403 PAID_PLAN_REQUIRED. Send a category, a note describing the affected tool and expected versus actual behavior, and the affected request_id, a relevant public url, or both. Use a url when no request_id is available; never invent an ID. Sanitize secrets and private data. Costs no credits. Report each distinct issue once; reporting the same request_id again returns the original feedback_id. If this tool fails, do not recursively report its failure or loop on retries.
update-monitor
ChatGPTUpdate an existing monitor's configuration, including its optional external webhook. Changes affect future runs, changing the target or change-detection definition creates a new baseline, and resuming a paused monitor (status=active) runs it promptly. Use get-monitor first when the current configuration must be preserved.
web-answers
ChatGPTResearch the live web and return a sourced answer in the exact JSON shape requested. Use fast for focused questions that should finish quickly or ultra for deeper research. Use web-search when ranked links or snippets are enough, or web-scrape with jsonParams when the source URL and extraction schema are already known.
web-crawl
ChatGPTStart from a URL, follow relevant internal links, and return clean Markdown for multiple pages in one synchronous request. Prefer responseMode="compact" for focused research; use full for complete page content or metadata. Use web-map for URLs only or submit-batch for large jobs that should run asynchronously.
web-map
ChatGPTMap a website's URLs using Context's index, with available page titles, descriptions, keywords, and languages. Filter by URL pattern or search phrase without retrieving every page body. Use web-scrape for one page, web-crawl for content from several pages, or submit-batch for large asynchronous collection.
web-scrape
ChatGPTScrape one known URL and return any combination of HTML, Markdown, a screenshot, page images, original bytes, CSS-selected fields, relevant highlights, schema-shaped JSON, or product data. Supports browser actions, custom target headers, PDF parsing, deadlines, and zero data retention. Browser clicks can change the target site's state. Prefer responseMode="compact" with formats.highlights and highlightsParams.query for focused research; use full for complete content or metadata. Use web-search when the URL is unknown, web-map for URLs only, web-crawl for linked pages, or submit-batch for large asynchronous jobs.
web-search
ChatGPTSearch the live web and optionally return Markdown or query-relevant highlights for ranked results in the same call. Prefer responseMode="compact" with highlightsOptions.enabled=true for focused research; use full for complete content or metadata. Use this to discover sources, answer current questions, or research a topic when the exact page URL is unknown. When a URL is already known, use web-scrape instead. Use web-answers when the user wants a sourced JSON answer rather than ranked links.
web-styleguide
ChatGPTExtract a website's design system, including colors, typography, spacing, shadows, and interface cues. Use this to reproduce a brand accurately in generated UI, design audits, or creative workflows.
brand-retrieve-unified
Claudecancel-batch
Claudecreate-monitor
Claudedelete-batch
Claudedelete-monitor
Claudeget-batch
Claudeget-batch-results
Claudeget-brand
Claudeget-change
Claudeget-monitor
Claudeget-monitor-run
Claudeget-news-search
Claudelist-account-runs
Claudelist-batches
Claudelist-changes
Claudelist-monitor-changes
Claudelist-monitor-credit-usage
Claudelist-monitor-runs
Claudelist-monitors
Claudeparse-document
Clauderun-monitor-now
Claudesend_feedback
Claudesubmit-batch
Claudeupdate-monitor
Claudeweb-crawl
Claudeweb-fonts
Claudeweb-naics
Claudeweb-scrape-html
Claudeweb-scrape-images
Claudeweb-scrape-markdown
Claudeweb-scrape-sitemap
Claudeweb-screenshot
Claudeweb-search
Claudeweb-sic
Claudeweb-styleguide
Claude
